971–980 of 1001 posts
My public blog response to this - and others saying the same thing - https://blog.herlein.com/post/domain-plus-software-superpowe... - Stop mourning the moat you thought you had. You have a much better one. You just need to pick up the new tool and start using it like it belongs in your hand.
I spent most of the last two years making a rather large hobby project. A 3D renderer for cad/visualization. It's pretty hard and slow work because getting anything wrong is usually hard to debug. Get a sign wrong and you have a black image suddenly, with painstaking debugging following. I worked on it for evenings and weekends, probably totaling a man-month of work or so. As a fun experiment, yesterday I asked a mod…
You knew exactly what you wanted, since you already built it. All decisions were already made, all tradeoffs reached. LLMs are definitely helpful, but try exploring something new with them and you'll slow down significantly.
I spent most of the last two years making a rather large hobby project. A 3D renderer for cad/visualization. It's pretty hard and slow work because getting anything wrong is usually hard to debug. Get a sign wrong and you have a black image suddenly, with painstaking debugging following. I worked on it for evenings and weekends, probably totaling a man-month of work or so. As a fun experiment, yesterday I asked a mod…
How many of the learnings over the past two years went into the prompt that you gave the model? Is it possible that you wouldn't have been able to prompt it so well without those learnings?
I spent most of the last two years making a rather large hobby project. A 3D renderer for cad/visualization. It's pretty hard and slow work because getting anything wrong is usually hard to debug. Get a sign wrong and you have a black image suddenly, with painstaking debugging following. I worked on it for evenings and weekends, probably totaling a man-month of work or so. As a fun experiment, yesterday I asked a mod…
Imagine taking up a hobby of drawing, then bemoaning the existence of a printer. Or learning spanish, and bemoaning google translate. Or trying out woodworking, and bemoaning IKEA.
I spent most of the last two years making a rather large hobby project. A 3D renderer for cad/visualization. It's pretty hard and slow work because getting anything wrong is usually hard to debug. Get a sign wrong and you have a black image suddenly, with painstaking debugging following. I worked on it for evenings and weekends, probably totaling a man-month of work or so. As a fun experiment, yesterday I asked a mod…
Which ide/tool/harness did you use?
I see many posts like this every month, and have many conversations with friends and colleagues who think the same, and I see two trends - like this author, they all joke about becoming carpenters, or electricians. Overwhelmingly, electricians. These two professions seem to be held in special regard by software engineers craving the simple life.
I hate to burst yet another bubble, but supply and demand economics apply here too folks. We can't all become electricians and carpenters. The work isn't there. In fact there's gonna be less work there than there is now of the economy tanks and nobody can afford to build or even renovate a house anymore
I spent most of the last two years making a rather large hobby project. A 3D renderer for cad/visualization. It's pretty hard and slow work because getting anything wrong is usually hard to debug. Get a sign wrong and you have a black image suddenly, with painstaking debugging following. I worked on it for evenings and weekends, probably totaling a man-month of work or so. As a fun experiment, yesterday I asked a mod…
Which ide/tool/harness did you use?
Earlier quoted context omitted.
Posting this under a burner so I don't dox myself: I work in FinTech on a regulated product. We have access to Mythos. Mythos identified part of our codebase that it confidently asserted was not complaint with a particular regulation and we were at grave risk by allowing it to operate the way it was. Except this was not the case, it had of course hallucinated what the regulation actually required (I know this because…
I have worked on highly regulated areas in finance (risk). Compliance is a highly creative art, often requiring lots of out-of-the-box thinking and non-obvious solutions. The people I found worst at this were IT. They tend to over-interpret regulation, and super-restrict beyond what is needed for actual de-facto compliance. My guess is the model makes the same mistakes as the programmers: taking 'rules' literally, un…
Isnt it how we make stable, deterministic and predictable system? How do you want to create one with ambiguous rules?
Earlier quoted context omitted.
You shouldn’t be bothered that someone else does your hobby better. It’s a hobby, it’s meant to be for you, for no purpose other than fun, experimentation, entertainment, what have you. The outcome isn’t as important as the process. That’s my take on this, at least. I’ll never be very good at Scythe, or the most creative role-player, certainly never managed to do anything beautiful in pottery class (although the glaz…
> you shouldn't be bothered that someone else does your hobby better I don't know, I'd feel this way a little. if it's something that's not obvious how much effort goes into the underlying process, it can feel pretty deflating if the craft behind it has felt like it's eliminated. I can't really think of a good example, but if my hobby was glueing precision glueing little 3d models, then suddenly the hobby has explode…
Aside: I had to get into puzzling to manage stress, my doctor actually ‘prescribed’ it, and hours go by while you mindlessly hunt for sky-blue pieces. There’s no point thinking about people that puzzle faster than you :)
I think we need to enjoy the process of things more. Life is precious. If someone else does your thing harder/faster/better/stronger, what are you gonna do? Doom-scroll? Nah, enjoy your special little thing.
Earlier quoted context omitted.
You knew exactly what you wanted, since you already built it. All decisions were already made, all tradeoffs reached. LLMs are definitely helpful, but try exploring something new with them and you'll slow down significantly.
Its surprising, how this key insight is lacking, even in the best of developers. It happened fast, as you prompted it just the right way. Another person, who doesn't have all that context in the mind, would fail quickly. For example I have decades of Software experience, but wont know where to even begin what OP did.
Simple, you start by asking LLM for more info.